Trustworthy Diagnostics With Out-of-Distribution Detection: A Novel Max-Consistency and Min-Similarity Guided Deep Ensembles for Uncertainty Estimation

The unknow fault diagnosis technology in industrial systems implies significant engineering application value and opportunities. The difficulty stems from the fact that the unknown fault samples frequently originate from the diagnostic model’s unknow distribution, leading to an out-of-distribution (OOD) problem. An incorrect diagnosis in the diagnostic model might readily arise from this. To deal with this problem, this paper proposes a novel trustworthy fault diagnosis with out-of-distribution detection which can be applied on industrial systems and equipment. First, deep base learners (DBLs) with different activation functions are designed to construct the deep ensemble model. After that, use in-distribution (ID) inputs to train the initial deep ensemble model. Then, with the proposed max consistency and min similarity guided criterion, the DBLs of the initial ensemble model are chosen to reconstruct the ensemble model. Finally, the diagnostic results’ uncertainty of the reconstruct ensemble model is estimated to accurately determine the type of the sample to be diagnosed. To verify the effectiveness of the proposed method, two gearbox datasets were used to test the proposed method and the max consistency and min similarity guided criterion. The experimental results demonstrate that the proposed approach can accurately identify unknown fault samples in the gearbox.